Compressing music recordings into audio summaries

Oriol Nieto, Eric J. Humphrey, Juan Pablo Bello

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a criterion to generate audible summaries of music recordings that optimally explain a given track with mutually disjoint segments of itself. We represent audio as sequences of beat-synchronous harmonic features and use an exhaustive search to identify the best summary. To demonstrate the merit of this approach, we evaluate the criterion and show consistency across a collection of multiple recordings of different works. Finally, we present a fast algorithm that approximates the exhaustive search and allows us to automatically learn the hyperparameters of the algorithm for a given track.

Original languageEnglish (US)
Title of host publicationProceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012
Pages313-318
Number of pages6
StatePublished - 2012
Event13th International Society for Music Information Retrieval Conference, ISMIR 2012 - Porto, Portugal
Duration: Oct 8 2012Oct 12 2012

Other

Other13th International Society for Music Information Retrieval Conference, ISMIR 2012
CountryPortugal
CityPorto
Period10/8/1210/12/12

Fingerprint

Audio recordings
Summary
Audio Recordings
Music
Harmonics
Merit

ASJC Scopus subject areas

  • Music
  • Information Systems

Cite this

Nieto, O., Humphrey, E. J., & Bello, J. P. (2012). Compressing music recordings into audio summaries. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012 (pp. 313-318)

Compressing music recordings into audio summaries. / Nieto, Oriol; Humphrey, Eric J.; Bello, Juan Pablo.

Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. p. 313-318.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Nieto, O, Humphrey, EJ & Bello, JP 2012, Compressing music recordings into audio summaries. in Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. pp. 313-318, 13th International Society for Music Information Retrieval Conference, ISMIR 2012, Porto, Portugal, 10/8/12.
Nieto O, Humphrey EJ, Bello JP. Compressing music recordings into audio summaries. In Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. p. 313-318
Nieto, Oriol ; Humphrey, Eric J. ; Bello, Juan Pablo. / Compressing music recordings into audio summaries. Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012. 2012. pp. 313-318
@inproceedings{80abbffc4bd045518b1525fd0c5da888,
title = "Compressing music recordings into audio summaries",
abstract = "We present a criterion to generate audible summaries of music recordings that optimally explain a given track with mutually disjoint segments of itself. We represent audio as sequences of beat-synchronous harmonic features and use an exhaustive search to identify the best summary. To demonstrate the merit of this approach, we evaluate the criterion and show consistency across a collection of multiple recordings of different works. Finally, we present a fast algorithm that approximates the exhaustive search and allows us to automatically learn the hyperparameters of the algorithm for a given track.",
author = "Oriol Nieto and Humphrey, {Eric J.} and Bello, {Juan Pablo}",
year = "2012",
language = "English (US)",
isbn = "9789727521449",
pages = "313--318",
booktitle = "Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012",

}

TY - GEN

T1 - Compressing music recordings into audio summaries

AU - Nieto, Oriol

AU - Humphrey, Eric J.

AU - Bello, Juan Pablo

PY - 2012

Y1 - 2012

N2 - We present a criterion to generate audible summaries of music recordings that optimally explain a given track with mutually disjoint segments of itself. We represent audio as sequences of beat-synchronous harmonic features and use an exhaustive search to identify the best summary. To demonstrate the merit of this approach, we evaluate the criterion and show consistency across a collection of multiple recordings of different works. Finally, we present a fast algorithm that approximates the exhaustive search and allows us to automatically learn the hyperparameters of the algorithm for a given track.

AB - We present a criterion to generate audible summaries of music recordings that optimally explain a given track with mutually disjoint segments of itself. We represent audio as sequences of beat-synchronous harmonic features and use an exhaustive search to identify the best summary. To demonstrate the merit of this approach, we evaluate the criterion and show consistency across a collection of multiple recordings of different works. Finally, we present a fast algorithm that approximates the exhaustive search and allows us to automatically learn the hyperparameters of the algorithm for a given track.

UR - http://www.scopus.com/inward/record.url?scp=84873423876&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873423876&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789727521449

SP - 313

EP - 318

BT - Proceedings of the 13th International Society for Music Information Retrieval Conference, ISMIR 2012

ER -